Radio Frequency Tagging–enabled patient monitoring: integrating mobility tracking with early warning systems for enhanced safety

Sep 30, 2026

Ensuring patient safety in healthcare environments requires continuous monitoring systems capable of identifying early warning signs of clinical risk. Traditional surveillance methods often fail to capture meaningful patterns in patient movement, limiting their ability to prevent incidents such as falls, prolonged immobility, or unnoticed health deterioration. Radio Frequency Tagging technology enables real-time patient tracking but existing solutions often lack predictive insights into patient behaviour. This study proposes an RFT-based framework combining spatio-temporal learning with dynamic similarity analysis and anomaly scoring fused with clinical indicators to trigger proactive alerts. Evaluated on a hybrid dataset with tagging traces and physiological/activity data, the Dynamic Time Warping-based anomaly detection achieved accuracy 87.5%–91.0%, sensitivity 88.4%–96.2%, and F1-scores up to 93.5%, distinguishing normal from abnormal movement patterns for context-aware, reliable continuous monitoring.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Abstract

Introduction

Abugabah etal. BioData Mining (2026) 19:2 [https://doi.org/10.1186/s13040-025-00504-2](https://doi.org/10.1186/s13040-025-00504-2) BioData Mining RESEARCH Open Access Radio Frequency Tagging–enabled patient monitoring: integrating mobility tracking with early warning systems for enhanced safety Ahed Abugabah 1, Prashant Kumar Shukla2, Piyush Kumar Shukla3 and Abhishek Dwivedi4* *Correspondence: Abhishek Dwivedi abhishek. dwivedi@jaipur. manipal. edu 1College of Technological Innovation, Zayed University, Abu Dhabi, United Arab Emirates 2Department of Computer Science and Engineering & Deputy Dean Research (ASET), Amity School of Engineering and Technology (ASET), Amity University, Mumbai, Maharashtra 410206, India 3Department of Computer Science & Engineering, University Institute of Technology, Rajiv Gandhi Proudyogiki Vishwavidyalaya (State Technological University of Madhya Pradesh), Bhopal, Madhya Pradesh, India 4Department of Data Science and Engineering, School of Computer Science & Engineering, Manipal University Jaipur, Jaipur, Rajasthan, India Abstract Ensuring patient safety in healthcare environments requires continuous monitoring systems capable of identifying early warning signs of clinical risk. Traditional surveillance methods often fail to capture meaningful patterns in patient movement, limiting their ability to prevent incidents such as falls, prolonged immobility, or unnoticed health deterioration. Radio Frequency Tagging technology has been increasingly adopted for real-time patient tracking; however, existing systems are generally limited to location detection and lack predictive insights into patient behaviour. To overcome these limitations, this study presents a Radio Frequency Tagging-based patient monitoring framework that integrates mobility tracking with an early warning mechanism to enable proactive health-care interventions. The proposed system uses a spatio-temporal probabilistic network to learn typical movement patterns from historical tagging data and applies a dynamic similarity analysis to detect deviations in real time. Anomaly scores generated from these comparisons are combined with clinical indicators to produce automated alerts for healthcare providers, supporting timely and informed responses. The framework is evaluated on a hybrid dataset comprising simulated tagging traces and publicly available physiological and activity data, including measurements of heart rate, respiration, and physical movement. The Dynamic Time Warping-based anomaly detection system achieved consistently high performance across all patient categories, with accuracy ranging from 87. 5% to 91. 0%, sensitivity between 88.4% and 96. 2%, and F1-scores up to 93. 5%, demonstrating its strong capability to effectively distinguish between normal and abnormal movement patterns across diverse clinical conditions. By combining location-based surveillance with predictive modelling and clinical scoring, the framework offers a context-aware and reliable tool for continuous patient monitoring, thereby enhancing safety and supporting datadriven clinical decision-making. Clinical trial number Not applicable. © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intend

FAQs

What limitation do traditional and existing monitoring approaches face in patient safety?

Traditional surveillance often misses meaningful movement patterns, and many RFID/RFT systems focus on passive location detection without predictive insights that support actionable clinical decisions.

How does the proposed framework detect early clinical risks?

It learns typical spatio-temporal movement patterns from historical tagging data, performs dynamic similarity analysis to find real-time deviations, and combines anomaly scores with clinical indicators to produce automated alerts.

What dataset and evaluation results support the framework’s performance?

Evaluation uses a hybrid dataset with simulated tagging traces and publicly available physiological and activity data (e.g., heart rate, respiration, and movement). The DTW-based anomaly detection reports accuracy 87.5%–91.0%, sensitivity 88.4%–96.2%, and F1-scores up to 93.5% across patient categories.

Sep 30, 2026

Upload by kopisore